{"id":"W3115064635","doi":"10.21611/qirt.2020.012","title":"Automatic Defects Segmentation and Identification by Deep Learning Algorithm with Pulsed Thermography: Synthetic and Experimental Data","year":2020,"lang":"en","type":"article","venue":"Proceedings of the 2020 International Conference on Quantitative InfraRed Thermography","topic":"Thermography and Photoacoustic Techniques","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Université Laval","keywords":"Thermography; Artificial intelligence; Artificial neural network; Segmentation; Deep learning; Computer science; Identification (biology); Synthetic data; Nondestructive testing; Pattern recognition (psychology); Test data; Infrared; Computer vision; Machine learning; Optics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001581546,0.0002397097,0.0002057883,0.0001406838,0.0001091978,0.000143983,0.0005131113,0.00006302626,0.00005435615],"category_scores_gemma":[0.00004524236,0.0001858992,0.00005627341,0.0004039021,0.0002777405,0.0004090991,0.0001054045,0.0002411235,5.389978e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000121187,"about_ca_system_score_gemma":0.000006932869,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006091308,"about_ca_topic_score_gemma":5.05394e-7,"domain_scores_codex":[0.9988488,0.00002800322,0.0002839528,0.0003622138,0.0003331164,0.0001438959],"domain_scores_gemma":[0.9993559,0.00008364538,0.0002165174,0.0001164113,0.0001517197,0.00007584836],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001926984,0.00009064241,0.003375184,0.0002043165,0.0006419128,0.000001044386,0.006628555,0.00005624703,0.9579667,0.007695151,0.0003096295,0.02283793],"study_design_scores_gemma":[0.001201077,0.0009593196,0.01124408,0.0005209228,0.0001964034,0.00001403518,0.01081534,0.6297917,0.3397189,0.004687404,0.000149055,0.0007018073],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9914134,0.0008438526,0.004560398,0.000224141,0.00007567288,0.0005780388,0.0004858295,0.0002866023,0.001532034],"genre_scores_gemma":[0.9967999,0.0002643937,0.00269832,0.00006651843,0.00001607326,0.00006753466,0.00004849752,0.00003395281,0.000004740527],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6297354,"threshold_uncertainty_score":0.7580751,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0208852537303778,"score_gpt":0.2545034701786091,"score_spread":0.2336182164482313,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}